Merging Health Indicators Using Transformed Belonging Functions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current health indicator merging methods for monitoring devices, such as rotary wing aircraft, may fail to detect all faults and can generate false alarms due to limitations in modeling the healthy-state model and comparing merged health indicators with alarm thresholds.
Innovation Solution
A method that combines detection thresholds with an alarm threshold for merging health indicators, using a transformation of the belonging function to account for individual health indicator detection thresholds, ensuring accurate fault detection and reducing inconsistencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If health indicators are merged using a simple healthy-state model, then the device complexity is reduced, but the fault detection precision deteriorates leading to false alarms or missed faults
Solution Approach 1:
The patent introduces a transformation of the belonging function as an intermediary mechanism between the healthy-state model and detection thresholds. This transformation adjusts the merged health indicator values to account for individual indicator detection thresholds, ensuring that the merging process respects the specific fault detection criteria of each indicator while maintaining overall system simplicity
Solution Approach 2:
The patent modifies the belonging function parameters through transformation to incorporate detection threshold information. By changing the parameters of the belonging function (specifically adjusting how merged indicators are compared against the alarm threshold), the system achieves both simplicity and precision in fault detection
2Measurement precision
If individual detection thresholds for each health indicator are considered in the merging process, then the fault detection precision is improved, but the device complexity increases
Solution Approach 1:
The patent merges the consideration of individual detection thresholds into a single transformed belonging function. Instead of handling each threshold separately (which would increase complexity), the system combines all threshold information into one unified transformation of the belonging function, maintaining simplicity while achieving precise fault detection
3Reliability
If the alarm threshold is set to be consistent with all individual detection thresholds, then the reliability of fault detection is improved, but the ease of operation deteriorates due to increased complexity in threshold management
Solution Approach 1:
The transformation of the belonging function performs self-adjustment to ensure consistency with individual detection thresholds. The system automatically incorporates threshold information into the merging process without requiring manual intervention to manage multiple thresholds, thereby maintaining reliability while preserving ease of operation
Data Source
AI summary
A method and system for merging health indicators of a device. During the method, health indicators Indi are firstly distributed in at least one indicator group G, each health indicator Indi being associated with a respective detection threshold Sdi, it being possible to determine a characteristic operating point of the device by using the health indicators Indi of an indicator group G. An alarm threshold Sa is determined using training health indicators. Then, a merged health indicator MHI is determined by taking into account both of the alarm threshold Sa and also of the detection thresholds Sdi of the health indicators Indi of the group G. Finally, the merged health indicator MHI is compared to the alarm threshold Sa and it is deduced whether or not the device presents a fault or a risk of such a fault appearing.